Video To Audio
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("sonilo/v1.1/video-to-sound-effects", {
input: {
video_url: "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4"
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
The client API provides a convenient way to submit requests to the model.
import { fal } from "@fal-ai/client";
const { request_id } = await fal.queue.submit("sonilo/v1.1/video-to-sound-effects", {
input: {
video_url: "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4"
},
webhookUrl: "https://optional.webhook.url/for/results",
});You can fetch the status of a request to check if it is completed or still in progress.
import { fal } from "@fal-ai/client";
const status = await fal.queue.status("sonilo/v1.1/video-to-sound-effects", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.
import { fal } from "@fal-ai/client";
const result = await fal.queue.result("sonilo/v1.1/video-to-sound-effects", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.
You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.
You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.
We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.
import { fal } from "@fal-ai/client";
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
video_url string* requiredThe video to add sound to (public URL, or upload a file). The generated audio matches the video's length.
prompt stringOptional. Describe the kind of sound you want; it steers the generated audio for every scene. Leave empty to caption the video automatically.
Optional. Split the video into time ranges, each with its own sound description. Leave empty to split into scenes automatically.
audio_format AudioFormatEnumFormat of the returned audio file: aac (default), mp3, wav, or flac. (The video with sound is always AAC.) Default value: "aac"
Possible enum values: wav, mp3, aac, flac
keep_speech_vocal booleanKeep the original video's speech/vocals. When on, the source audio is separated (music source separation) and the isolated vocals are kept as recorded, with the generated sound mixed in at a level matched to the voice; the rest of the original soundtrack (music, ambience) is dropped. Applies to the returned audio and video. When off (default), the result carries only the generated sound.
{
"video_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4",
"segments": [
{}
],
"audio_format": "aac"
}The generated sound, in your chosen audio format.
All generated sounds, one per sample.
Present when the audio carries the inaudible provenance watermark.
The segments the audio was generated in, in source video order.
{
"audio": {
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
},
"audios": [
{
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
],
"segments": [
{
"meta": {}
}
]
}index integer* requiredPosition of the segment, in source video order.
start float* requiredStart in seconds on the source video timeline.
end float* requiredEnd in seconds on the source video timeline.
scheme stringWatermark scheme identifier. Default value: "sc44k-1"
message_hex string* requiredThe 40-bit message embedded in the audio, hex.
url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
start floatSegment start time in seconds (from video start). The FIRST segment's start must be 0.
end floatSegment end time in seconds. Must equal the next segment's start (contiguous; no gaps/overlaps); the last segment's end must be <= the video duration.
prompt stringSFX / foley description for this segment. Default value: ""
Short display labels for the sounds in this segment; may be empty.
skipped booleanWhether this segment was left silent. Always false on sfx-v1.0, which generates every segment.
skip_reason stringWhy the segment was left silent, when it was.